© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37042
    Prev
    Next
    INDEX
    Explanations

    update status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iest
    -0.11
    reira
    -0.10
    /her
    -0.10
    ×ķר
    -0.10
    åºķä¸ĭ
    -0.09
    ä¼Łå¤§çļĦ
    -0.09
    untime
    -0.09
    /bit
    -0.09
    Į
    -0.08
    ware
    -0.08
    POSITIVE LOGITS
    OrCreate
    0.16
    åĴĮå®ĮåĸĦ
    0.12
    pressive
    0.11
    é¢ĸ
    0.11
    prising
    0.10
    ми
    0.10
    ient
    0.09
    ary
    0.09
    æ¢
    0.09
    erior
    0.08
    Activations Density 0.044%

    No Known Activations